공개 Claude Code 마켓플레이스의 플러그인 34개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
필터와 일치하는 34개의 플러그인을 표시합니다.
lawve-ailawve-ai/awesome-legal-skills2
awesome-journal-skillsbrycewang-stanford/Awesome-Journal-Skills1
claude-code-skillsalirezarezvani/claude-skills1
research-paper-lifecycle-skillsShaishavMaisuria/research-paper-lifecycle-skills1.claude-plugin/marketplace.json이 포함된 repo를 제출하면 모든 plugin을 목록에 추가합니다.
marketplace 제출
Twelve-skill bundle covering the 《经济学(季刊)》 manuscript lifecycle: workflow router, fit positioning, internationally-legible topic selection, field-benchmarked literature review, structural / quasi-experimental identification, modern staggered-DID compliance, inference rigor, mechanism evidence, figures-over-tables, English abstract, submission preflight, and rebuttal.
academicKnowledge base compiled from OpenAI's Spinning Up in Deep RL (MIT, Joshua Achiam) by engineering/book-to-skill. A resident core carries the RL optimization problem, the model-free taxonomy, the policy-gradient template with its five valid weights, the safe-step family (VPG to TRPO to PPO) and the overestimation family (DDPG to TD3 and SAC); 20 on-demand chapters cover key concepts and MDPs, the algorithm taxonomy and model bias, the policy gradient derivation with the log-derivative trick and EGLP lemma, Achiam's researcher essay, the key-papers topic map, the exercises including the silent DDPG broadcasting bug, the benchmark parity disclosure, one chapter per algorithm, and the logger/MPI/ExperimentGrid utilities. Ships a glossary, a patterns file with 16 techniques, a decision cheatsheet with thresholds, a cs-spinning-up-deep-rl agent and /cs-spinning-up-deep-rl. Structured study notes, not a reproduction of the source.
The post-draft lifecycle nobody else covers: CFP requirement parsing, venue/track selection and tailoring, desk-reject preflight, anonymization, review triage, benchmark scorecards, rebuttals in all three real formats, and camera-ready rails for ACM and IEEE.
32 Claude skills for planning, recruiting, running, synthesising and sharing user research, from the research plan to the repository, in seven stages: plan the study with what is already known, the assumptions that carry the risk, the research plan, and a check on any "synthetic user" answer offered instead of real people; recruit and consent real participants with a recruitment brief, a screener, an informed consent form, a data handling plan, an incentive plan and a participant database; write the guides for interviews, moderated and unmoderated usability tests, benchmarks, surveys and diary studies; run and capture sessions through contextual inquiry, accessible sessions, AI feature studies and same-day debriefs; synthesise with every quote kept through thematic analysis, usability findings, survey analysis, insight statements and an evidence trace audit; turn findings into a journey map, jobs to be done statements and an opportunity solution tree; then share and reuse them in a rea
productivityClaude Guide for Training Impact: 30 Claude skills for proving what a training programme changed, from the request to the decision about what comes next, in seven stages: question the request with a request brief, sponsor discovery questions and a performance problem diagnosis; agree what proof looks like with a critical behaviours map, a success measures agreement and a baseline plan; collect the evidence with two surveys, an observation checklist, an interview guide and a data request; read it honestly in a before-and-after results table and a contribution analysis; tell the sponsor with success cases, a return as a range and a one-pager; report to the business with a metrics set, a quarterly report and an overclaim check; then feed it back through a review meeting, a decision record and a business case. For L&D managers, L&D specialists and L&D leaders. Claude plans the evaluation and drafts the report from your data; it never invents a result, a benchmark or a quote, and a named pe
productivitySix Xcode build optimization skills in one plugin: benchmark, compilation analysis, project analysis, SPM build analysis, a recommend-first orchestrator, and a fixer for applying approved changes.
developmentLoad testing and performance benchmarking with metrics analysis and bottleneck identification
vLLM operator reference suite — deployment, configuration, quantization, caching, KV, tool parsers, reasoning parsers, chat templates, benchmarking, performance tuning, observability, omni, input modalities, speculative decoding, NVIDIA hardware, and a Gemma 4 31B operating-point serve recipe.
inferenceRoutes any legal task to the right LLM, like OpenRouter but for legal work and grounded in benchmarks instead of brand loyalty. Built from mid-2026 legal evals (legalbenchmarks.ai, Vals AI × Stanford LegalBench across 124 models, Harvey's Legal Agent Benchmark, the Atticus Project's CUAD/MAUD/ACORD) plus translation evidence (WMT25, SwiLTra-Bench, ArabLegalEval). Covers five verticals: contract drafting, info extraction, legal research, contract review, and legal translation (including Arabic/MENA). Each asks up to four questions (cost, speed, accuracy/stakes, privacy/jurisdiction/language), then returns a primary model, a fallback, what to avoid, and what a human must verify. Core principle: capability is not controllability, so every route ends with a verification step. Not legal advice; a lawyer owns the output.
Test whether your Claude Code skills actually trigger, and benchmark any coding agent — author, run, and analyze the eval suite that proves it, locally or as a CI gate.
testing4 industry-analysis skills: peer benchmarking, sector overview, competitive positioning, and supply-chain mapping.
Email marketing operating manual for AI agents, with hard send-safety gates: campaigns, newsletters and flows, deliverability and DNS, switching ESPs, compliance, anti-slop copy, email design and benchmarks, with any ESP through MCP or an API.
28 working methods for performance: algorithmic-optimization, async-io-patterns, batching-and-debouncing, benchmark-design, and more
Ten giveaway skills: generate concepts, choose or evaluate a prize, plan entry actions, set run length and start date, structure winners and terms, plan promotion, run a provably fair draw seeded from a public beacon, write every winner message, review results against benchmarks, and set up the campaign in Gleam
Expert CIS Controls v8 (CIS Top 18) advisor — implementation group scoping (IG1/IG2/IG3), control gap assessments, safeguard-level guidance, asset inventory, software inventory, data protection, secure configuration, account management, access control, continuous vulnerability management, audit log management, email and web browser protections, malware defenses, network infrastructure management, network monitoring and defense, application software security, incident response, penetration testing, and CIS Controls mapping to NIST CSF, ISO 27001, SOC 2, and CMMC. Use for any question about CIS Controls, CIS Benchmarks, Implementation Groups, or prioritized cyber hygiene for any organization size.
Search relevance testing for Elasticsearch, OpenSearch, Solr, vector and hybrid search: judgment lists and NDCG, MRR and recall@k regression checks. Builds judgment lists with rater guidelines, benchmarks vector recall against latency, and measures fusion lift in hybrid pipelines. A review agent (relevance-regression-reviewer) compares before and after metrics per query.
ai-mlOperate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.
Design organizational topology, talent, rewards, culture, and health decisions with explicit decision rights and validation. Do not use for legal advice, project delivery planning, financial modeling, or technology implementation. reporting structures), talent strategy (make-vs-buy, skill taxonomies, succession planning), compensation frameworks (market benchmarking, equity design, leveling), culture architecture (values codification, rituals, psychological safety), organizational health metrics (eNPS, retention risk, engagement surveys), DEI strategy (inclusive design, equitable systems, belonging).
Optimize software performance through user-journey baselines, profiling, representative benchmarks, controlled experiments, and field verification. Use when asked to make an application, service, workflow, or hot path faster or more efficient, or to build the measurement loop first. Do not use for a reliability incident, capacity forecast, generic product A/B test, or operating a named telemetry or load-testing tool without an optimization objective.
Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API serving, throughput and latency benchmarking, continuous batching tuning, GPU operation, and upgrade/rollback. Use when deploying or running a vLLM server (vllm serve, vllm/vllm-openai), sizing a model and its KV cache for GPUs, selecting quantization and parallelism, serving via /v1 endpoints, measuring serving throughput or latency, tuning batching, or diagnosing GPU, OOM, or startup failures in a vLLM deployment. Do not use for model training, fine-tuning, evaluation-set design, or engine-selection methodology (that is ml-engineering), or for operating the llama.cpp stack with GGUF models (that is llama-cpp); other inference engines (TGI, Ollama, Triton) are out of scope.
